Xu Zhikun, Yao Shihua, Jiang Zhongji, Hu Linhui, Huang Zijun, Zeng Quanjun, Liu Xueyan
Department of Critical Care Medicine, Shenzhen People's Hospital, First Affiliated Hospital of Southern University of Science and Technology, The Second Affiliated Hospital of Jinan University, Shenzhen 518020, China.
Division of Cardiovascular Surgery, Cardiac and Vascular Center, The University of Hong Kong-Shenzhen Hospital, Shenzhen 518053, China.
Heart Lung. 2023 Nov-Dec;62:207-214. doi: 10.1016/j.hrtlng.2023.08.001. Epub 2023 Aug 9.
Accurately forecasting patients admitted to the intensive care units (ICUs) after surgery may improve clinical outcomes and guide the allocation of expensive and limited ICU resources. However, studies on predicting postoperative ICU admission in non-cardiac surgery have been limited.
To develop and validate a prediction model combining pre- and intraoperative variables to predict ICU admission after non-cardiac surgery.
This study is based on data from the Vital Signs DataBase (VitalDB) database. Predictors were selected using the least absolute shrinkage and selection operator regression method and logistic regression to develop a nomogram and an online web calculator. The model was internally verified by 1000-Bootstrap resampling. Performance of model was evaluated using area under the receiver operating characteristic curve (AUC), calibration curve and Brier score. The Youden's index was used to find the optimal nomogram's probability threshold. Clinical utility was assessed by decision curve analysis.
This study included 5216 non-cardiac surgery patients; of these, 812 (15.6%) required postoperative ICU admission. Potential predictors included age, ASA classification, surgical department, emergency surgery, preoperative albumin level, preoperative urea nitrogen level, intraoperative crystalloid, intraoperative transfusion, intraoperative catheterization, and surgical time. A nomogram was constructed with an AUC of 0.917 (95% CI: 0.907-0.926) and a Brier score of 0.077. The Bootstrap-adjusted AUC was 0.914; the adjusted Brier score was 0.078. The calibration curve showed good agreement between predicted and actual probabilities; and the decision curve indicated clinical usefulness. Finally, we established an online web calculator for clinical application (https://xuzhikun.shinyapps.io/postopICUadmission1/).
We developed and internally validated an easy-to-use nomogram for predicting ICU admission after non-cardiac surgery.
准确预测术后入住重症监护病房（ICU）的患者，可能会改善临床结局，并指导对昂贵且有限的ICU资源进行分配。然而，关于非心脏手术术后入住ICU的预测研究有限。
开发并验证一个结合术前和术中变量的预测模型，以预测非心脏手术后的ICU入住情况。
本研究基于生命体征数据库（VitalDB）的数据。采用最小绝对收缩和选择算子回归方法及逻辑回归选择预测因子，以建立列线图和在线网络计算器。该模型通过1000次自抽样重采样进行内部验证。使用受试者操作特征曲线下面积（AUC）、校准曲线和Brier评分评估模型性能。用约登指数确定最佳列线图的概率阈值。通过决策曲线分析评估临床实用性。
本研究纳入了5216例非心脏手术患者；其中，812例（15.6%）术后需要入住ICU。潜在预测因子包括年龄、美国麻醉医师协会（ASA）分级、手术科室、急诊手术、术前白蛋白水平、术前尿素氮水平、术中晶体液、术中输血、术中置管和手术时间。构建的列线图AUC为0.917（95%CI：0.907 - 0.926），Brier评分为0.077。自抽样调整后的AUC为0.914；调整后的Brier评分为0.078。校准曲线显示预测概率与实际概率之间具有良好的一致性；决策曲线表明该模型具有临床实用性。最后，我们建立了一个用于临床应用的在线网络计算器（https://xuzhikun.shinyapps.io/postopICUadmission1/）。
我们开发并在内部验证了一个易于使用的列线图，用于预测非心脏手术后的ICU入住情况。
